© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54076
    Prev
    Next
    INDEX
    Explanations

    center or institute followed by location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åł°
    -0.11
    esser
    -0.11
    imar
    -0.10
    bab
    -0.09
    åĺĪ
    -0.09
    åIJ±
    -0.09
    ober
    -0.09
     McGr
    -0.09
    uga
    -0.09
    obi
    -0.08
    POSITIVE LOGITS
    ãĥ¬ãĥ¼
    0.09
    é«ĺä½İ
    0.09
    箬
    0.09
    çªĸ
    0.08
    ç¦ıå¾·
    0.08
    æ¼Ĥ亮
    0.08
    ç«Ļèµ·æĿ¥
    0.08
     disqualified
    0.08
    èµł
    0.08
    çĸ¯
    0.08
    Activations Density 0.200%

    No Known Activations